Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manus
    -0.07
    regex
    -0.06
    ertiary
    -0.06
    listeners
    -0.06
    jsonData
    -0.06
     kế
    -0.05
    んです
    -0.05
    時の
    -0.05
     countdown
    -0.05
    -esque
    -0.05
    POSITIVE LOGITS
     util
    0.08
    (si
    0.07
    に入
    0.06
    :str
    0.06
    .mongo
    0.06
     uri
    0.06
     ear
    0.06
    void
    0.06
     symmetry
    0.06
     النه
    0.06
    Act Density 0.011%

    No Known Activations